Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    function arguments and parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sviluppo
    0.47
     üks
    0.45
     of
    0.44
     för
    0.43
     oli
    0.43
     stencil
    0.43
     innovative
    0.43
     it
    0.42
     innovate
    0.42
    Akh
    0.42
    POSITIVE LOGITS
     MDLVertex
    0.45
    시키는
    0.45
    тесь
    0.44
    ीडी
    0.43
     музыка
    0.42
     loudly
    0.42
    রাও
    0.42
     gravely
    0.41
    📏
    0.41
     слу
    0.41
    Act Density 0.000%

    No Known Activations